Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1616 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0758. Min Act: -0.0000

Data Index: 775919 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0834. Min Act: -0.0000

Data Index: 760287 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0796. Min Act: -0.0000

Data Index: 436371 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0709. Min Act: -0.0000

Data Index: 449707 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0721. Min Act: -0.0000

Data Index: 956698 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0673. Min Act: -0.0000

Data Index: 1578751 (Python Code)

Max Activating Token Index: 1006

Text #6

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0603. Min Act: -0.0000

Data Index: 30452 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1497063 (Python Code)

Max Activating Token Index: 798

Text #8

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0620. Min Act: -0.0000

Data Index: 1129920 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1430252 (Python Code)

Max Activating Token Index: 517

Text #10

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0608. Min Act: -0.0000

Data Index: 198539 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0500. Min Act: -0.0000

Data Index: 503332 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0505. Min Act: -0.0000

Data Index: 374010 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1443083 (Python Code)

Max Activating Token Index: 245

Text #14

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0509. Min Act: -0.0000

Data Index: 186436 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0503. Min Act: -0.0000

Data Index: 626520 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1031508 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0513. Min Act: -0.0000

Data Index: 370179 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1180589 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1574491 (Python Code)

Max Activating Token Index: 966